Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4417 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2106. Min Range: -1.2106

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1588869 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 1.2106. Min Range: -1.2106

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1270585 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 1.2106. Min Range: -1.2106

Max Act: 1.0123. Min Act: -0.0000

Data Index: 54755 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 1.2106. Min Range: -1.2106

Max Act: 1.0680. Min Act: -0.0000

Data Index: 701651 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9614. Min Act: -0.0000

Data Index: 917100 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1679814 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1237872 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1008313 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8967. Min Act: -0.0000

Data Index: 117080 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1146917 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8905. Min Act: -0.0000

Data Index: 962044 (The Pile)

Max Activating Token Index: 280

Text #11

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9438. Min Act: -0.0000

Data Index: 31399 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8524. Min Act: -0.0000

Data Index: 641501 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1426818 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1796095 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8278. Min Act: -0.0000

Data Index: 751273 (The Pile)

Max Activating Token Index: 611

Text #16

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.9021. Min Act: -0.0000

Data Index: 881870 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1597000 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1249143 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 1.2106. Min Range: -1.2106

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1638381 (The Pile)

Max Activating Token Index: 33